806-regulations-eu-data-act
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because its core function involves the agent reading and interpreting untrusted data sources, such as Java source code, DTOs, Kafka contracts, and system documentation. Malicious instructions placed within these materials (e.g., in code comments) could potentially bias the agent's audit results.
- Ingestion points: The agent ingests Java source code, API contracts, DTOs, serializers, schema registries, Kafka contracts, and cloud provider documentation as described in the workflow (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructional guards to prevent the agent from following instructions embedded in the audited artifacts.
- Capability inventory: The skill's capabilities are limited to generating structured markdown reports; it does not utilize dangerous tools such as shell execution, dynamic code interpretation, or unauthorized network operations.
- Sanitization: No sanitization or filtering logic is specified for the external data being processed.
Audit Metadata